Applied and Computational Engineering

- The Open Access Proceedings Series for Conferences


Proceedings of the 4th International Conference on Signal Processing and Machine Learning

Series Vol. 52 , 27 March 2024


Open Access | Article

An analysis of different methods for deep neural network pruning

Longxiang Gou * 1 , Ziyi Han 2 , Zhimeng Yuan 3
1 University of Hong Kong
2 Northwest University
3 Beijing Institute of Technology

* Author to whom correspondence should be addressed.

Applied and Computational Engineering, Vol. 52, 81-86
Published 27 March 2024. © 27 March 2024 The Author(s). Published by EWA Publishing
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Citation Longxiang Gou, Ziyi Han, Zhimeng Yuan. An analysis of different methods for deep neural network pruning. ACE (2024) Vol. 52: 81-86. DOI: 10.54254/2755-2721/52/20241292.

Abstract

Neural network pruning, the process of removing unnecessary weights or neurons from a neural network model, has become an essential technique for reducing computational cost and increasing processing speed, thereby improving overall performance. This article has grouped current pruning methods into three classes—channel pruning, filter pruning, and parameter sparsification—and discussed how each method works. Each approach has its own strengths: channel pruning is particularly useful for reducing model depth and width, filter pruning is more suitable for maintaining model depth while decreasing storage requirements, and parameter sparsification can be applied across various network architectures to achieve both storage and computational efficiency. This work will delve into how each method works and highlight key related works of each category. In the future, it is expected that future research in neural network pruning could focus on developing more sophisticated techniques that can automatically identify important weights or neurons within a network.

Keywords

Neural network pruning, Deep learning, Parameter sparsification

References

1. He, Y., Zhang, X., & Sun, J. (2017). Channel pruning for accelerating very deep neural networks. In Proceedings of the IEEE international conference on computer vision, 1389-1397.

2. Zhang, M., Lu, Q., Li, W., & Song, H. (2021). Deep neural network compression algorithm based on combined dynamic pruning. Journal of Computer Applications, 41(6), 1589.

3. Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017). Learning efficient convolutional networks through network slimming. In Proceedings of the IEEE international conference on computer vision, 2736-2744.

4. Lin, M., Ji, R., Zhang, Y., Zhang, B., Wu, Y., & Tian, Y. (2020). Channel pruning via automatic structure search. arXiv preprint arXiv:2001.08565.

5. Luo, J. H., Wu, J., & Lin, W. (2017). Thinet: A filter level pruning method for deep neural network compression. In Proceedings of the IEEE international conference on computer vision, 5058-5066.

6. He, Y., Ding, Y., Liu, P., Zhu, L., Zhang, H., & Yang, Y. (2020). Learning filter pruning criteria for deep convolutional neural networks acceleration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2009-2018.

7. He, Y., Liu, P., Wang, Z., Hu, Z., & Yang, Y. (2019). Filter pruning via geometric median for deep convolutional neural networks acceleration. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 4340-4349.

8. Lin, M., Ji, R., Wang, Y., Zhang, Y., Zhang, B., Tian, Y., & Shao, L. (2020). Hrank: Filter pruning using high-rank feature map. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 1529-1538.

9. Wu, J., Wu, H. N., Liu, A., Li, C. & Li, Q. S. (2019). A deep learning model compression method based on fusion of Lasso regression and SVD. Telecommunications Technology (05), 495-500.

10. Gong, K., Zhang, C., & Zeng, G. (2020). Convolutional neural network model pruning combined with tensor decomposition compression method. Comput. Appl, 40, 3146-3151.

Data Availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).

Volume Title
Proceedings of the 4th International Conference on Signal Processing and Machine Learning
ISBN (Print)
978-1-83558-349-4
ISBN (Online)
978-1-83558-350-0
Published Date
27 March 2024
Series
Applied and Computational Engineering
ISSN (Print)
2755-2721
ISSN (Online)
2755-273X
DOI
10.54254/2755-2721/52/20241292
Copyright
27 March 2024
Open Access
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited

Copyright © 2023 EWA Publishing. Unless Otherwise Stated